Automatic analysis of aqueous specimens for phytoplankton structure recognition and population estimation

Funding Acknowledgements Type of funding sources: Public grant(s) – EU funding. Main funding source(s): This publication is part of a project that has received funding from the European Union’s Horizon 2020 research and innovation program under grant agreement No 954783. Background Stereotactic arrhythmia radio-ablation (STAR) is a promising strategy for the non-invasive treatment of ventricular arrhythmias (VA). The management of the cardio-respiratory motion of the target and the reduction of the uncertainties related to patients’ positioning are two of the main challenges that STAR has to overcome. A prototype of a system was developed that can automatically acquire and interpret echocardiographic images using an artificial intelligence (AI) algorithm to calculate cardiac displacement in real-time. Purpose To evaluate the feasibility of this automatic acquisition system in patients with a history of VA. Methods We conducted a single center, feasibility study enrolling consecutive patients with a history of VA. Echocardiographic images were automatically acquired from the parasternal and apical views with a dedicated probe. The system was designed to hold the probe fixed to the chest in the supine position during both free-breathing and short expiratory breath-hold sequences, to simulate STAR treatment. The primary endpoint was the percentage of patients reaching a score ≥2 in a multi-parametric assessment evaluating the quality of automatically acquired images in terms of: A - allowing a proper identification of the cardiac cycle phase using the AI algorithm, B - allowing a correct measurement of the heart displacement by the AI algorithm, C - ability to visually distinguish typical cardiac structures, and D - stability of the image throughout the respiration cycle. Moreover, we investigated the potential impact of clinical and demographic characteristics on achieving the primary outcome. Results From May to September 2021, we enrolled 24 patients (63±14 years, 21% females). All of them had a history of VA and 21 (88%) had an ICD. Eight patients (33%) had coronary artery disease, 12 (50%) had non-ischemic cardiomyopathy, and 3 had idiopathic VA. Parasternal as well as apical images were obtained from all patients except from one, in whom parasternal view could not be collected due to the patient’s inability to maintain the supine position. The primary outcome was achieved in 23 patients (96%) for the apical view, in 20 patients (87%) for the parasternal view, and in all patients in at least one of the two views. The images quality was maximal (i.e. score=4) in at least one of the two windows in 19 patients (79%). Atrial fibrillation arrhythmia was the only clinical characteristics associated with a poor score outcome in both imaging windows (apical p=0,022, parasternal p=0,014). Conclusion An automatic ultrasonographic image acquisition system associated with an AI algorithm is feasible for real-time monitoring of cardiac motion in patients with a history of VA. The possibility of real-time, non-invasive monitoring of cardiac position would lead to a significant improvement in the quality and safety of STAR treatment, particularly in case of treatment with heavy particles such as protons and carbon ions.

High quality ground truth data sets are crucial for the development of image recognition systems. However, the task of annotating large image data sets manually takes a lot of time and effort. In order to lower the burden for the development of application-specific image recognition systems, we developed an advanced user interface. This interface is especially designed for non-expert users with little-to-no knowledge of computer vision techniques. The interface presents images clustered by similarity and allows for an efficient and simple annotation of large data sets. The integration of overview+detail concepts allows the precise navigation inside large data sets. The interface can be used without prior instructions on the underlying concepts, like self-organizing maps, image features or visualization techniques.

The structure of biocenosis is a powerful indicator for the condition of and changes in the quality of the ecosystem. Identification and quantification of populations of microorganisms enables an assessment of the effect of any stressor on it. A method and some results are presented using automatic image acquisition, evaluation and recognition to ease the time consuming part of manual organism recognition and counting at the microscope.

The global anime market continues to grow, character recognition is particularly important in the derivatives market. And the demand for anime content on various platforms continues to increase. However, relatively few studies have been conducted on anime character image recognition, and the current research focuses on image recognition using a single ResNet50 model, with few studies attempting to incorporate other models to improve recognition accuracy. This project aims to construct a Pokémon image recognition system using deep learning techniques to improve classification efficiency and accuracy. The project uses the Pokémon image dataset on kaggle and performs data preprocessing, including data balancing, de-noising, normalization and data enhancement. The project constructed a classification prediction model combining ResNet50 and SVM respectively, which achieved 97.25% accuracy, 97.11% recall and 97.15% F1 score on the test set, indicating that the model can effectively recognize different kinds of Pokémon images. This project verifies the effectiveness of the ResNet50 model in image recognition tasks and provides a useful reference for subsequent research on image recognition.

In the age of ever-increasing "-omics" studies, the accurate and statistically robust determination of microbial cell numbers within often-complex samples remains a key task in microbial ecology. Microscopic quantification is still the only method to enumerate specific subgroups of microbial clades within complex communities by, for example, fluorescence in situ hybridization (FISH). In this study, we improved an existing automatic image acquisition and cell enumeration system and adapted it for usage at high seas on board an oceanographic research ship. The system was evaluated by testing settings such as minimal pixel area and image exposure times ashore under stable laboratory conditions before being brought on board and tested under various wind and wave conditions. The system was robust enough to produce high-quality images even with ship heaves of up to 3 m and pitch and roll angles of up to 6.3°. On board the research ship, on average, 25% of the images acquired from plankton samples on filter membranes could be used for cell enumeration. Automated enumeration was highly correlated with manual counts (r(2) > 0.9). Even the smallest of microbial cells in the open ocean, members of the alphaproteobacterial SAR11 clade, could be confidently detected and enumerated. The automated image acquisition and cell enumeration system developed here enables an accurate and reproducible determination of microbial cell counts in planktonic samples and allows insight into the abundance and distribution of specific microorganisms already on board within a few hours.IMPORTANCE In this research article, we report on a new system and software pipeline, which allows for an easy and quick image acquisition and the subsequent enumeration of cells in the acquired images. We put this pipeline through vigorous testing and compared it to manual microscopy counts of microbial cells on membrane filters. Furthermore, we tested this system at sea on board a marine research vessel and counted bacteria on board within a few hours after the retrieval of water samples. The imaging and counting system described here has been successfully applied to a number of laboratory-based studies and allowed the quantification of thousands of samples and FISH preparations (see, e.g., H. Teeling, B. M. Fuchs, D. Becher, C. Klockow, A. Gardebrecht, C. M. Bennke, M. Kassabgy, S. Huang, A. J. Mann, J. Waldmann, M. Weber, A. Klindworth, A. Otto, J. Lange, J. Bernhardt, C. Reinsch, M. Hecker, J. Peplies, F. D. Bockelmann, U. Callies, G. Gerdts, A. Wichels, K. H. Wiltshire, F. O. Glöckner, T. Schweder, and R. Amann, Science 336:608-611, 2012, http://dx.doi.org/10.1126/science.1218344). We adjusted the standard image acquisition software to withstand ship movements. This system will allow for more targeted sampling of the microbial community, leading to a better understanding of the role of microorganisms in the global oceans.

This research aims to design and implement a web-based teacher attendance system that utilizes facial recognition technology through the YOLOv8 algorithm as a solution to the conventional paper-based attendance system, which is prone to recording errors, data manipulation, and potential information loss. Data collection was conducted by recording short videos of 24 teachers and staff at SD Negeri 1 Purbalingga Lor under various lighting conditions and viewpoints, which were then converted into an image dataset using the Roboflow platform. The dataset was processed through several preprocessing stages including video-to-image conversion, image resizing, augmentation, and data splitting for training, validation, and testing purposes. The YOLOv8s model was chosen due to its ability to detect faces in real time with high accuracy, as demonstrated by training results showing an mAP of 98.6%, Precision of 97.8%, and Recall of 98.5%. The integration of the model into a backend Flask-based application enables the attendance process to be carried out automatically and in real time, while functional testing using the Black Box Testing method confirms that the face detection feature operates as designed, achieving an accuracy of 93% under optimal lighting conditions. Consequently, this research successfully presents an innovative digital solution that not only enhances the efficiency of attendance administration but also minimizes the risks of data manipulation and recording errors in educational environments.

Spiders are the most abundant predatory natural enemies in terrestrial ecosystems. As an important natural enemy of many agricultural and forestry pests, spiders play a very significant role in the biological control of pests. In order to make rational use of spider resources, it is necessary to observe and study the population characteristics of it. Direct observation method is time-consuming and laborious. If we can take the videos or images of spiders by surveillance cameras, and then use computer vision technology to identify and classify automatically, the efficiency of image data acquisition and pest biological control will be greatly improved. Motivated by this, we studied the classification and recognition of spider images in natural background obtained by common surveillance equipment. However, the images of some species of spiders in natural background are difficult to be collected, and the inadequate clarity and contrast of the subjects in images will also affect the recognition accuracy. So, firstly, histogram equalization was used to enhance the contrast of the image; the dataset of spider images was expanded by image rotation, reflection, flipping, zooming, translating and increasing the pixel noise appropriately, and so on; the contour detection was carried out for assistant recognition. Secondly, taken the deep convolutional neural networks (CNN) as our basic framework, two automatic recognition models of spider images, that is the 8-layer deep CNN model and the transfer learning model based on Inception-v3, were constructed. After that, the two models were trained, evaluated and compared under a dataset with 4478 pre-processed images. The experimental results show that the first model has a limited effect on image feature extraction of spiders in natural background, while the second model based on transfer learning can achieve better recognition accuracy when combining image contour features as an auxiliary input. In the second model, the accuracy of training set and testing set can reach more than 90%, and the recognition speed can be controlled within 1 second, which meets the practical requirements of automatic classification and recognition of spider images in natural background.

Bone tumors are one of the most common diseases in bone and soft tissue tumors, and accurate classification is crucial for developing effective treatment strategies. However, traditional pathological morphology diagnosis is subjective and uncertain, requiring highly specialized knowledge and experience. Therefore, how to efficiently and accurately classify bone tumor types based on pathological images is an urgent problem to be solved. In this study, a lightweight convolutional neural network (CNN) model called Efficient and Enhance Network (EENet) was proposed for the automatic recognition of bone tumor pathological images. The model introduced efficient channel attention (ECA) blocks to improve the efficiency of feature extraction and reduce computational complexity. A comprehensive dataset of bone pathological images, including five types of bone lesion tissues and normal bone tissue, was compiled for the research. Due to the low incidence of bone tumors and the difficulty in obtaining a large amount of data, the transfer learning method was chosen to overcome the problem of limited data volume. The experimental results from the fivefold cross‐validation demonstrate that the proposed model achieves 99.06% accuracy, 99.08% precision, 99.19% recall, 99.81% specificity, and 99.03% F1‐score in the bone tumor classification task, highlighting its potential as a clinical diagnostic tool.

Computerized automatic system to obtain inspiration/expiration chest roentgenograms without patient collaboration

In recent years, with the popularity of the Internet, digital media has become an indispensable part of people's life. Image acquisition equipment is widely used in daily life and work. However, due to technical problems, it can not meet the performance requirements of users. At the same time, a large number of data and information are difficult to be effectively processed, which also reduces the image quality, reduces the storage space and increases the image distortion. Therefore, it is necessary to develop new algorithms to improve these defects. Therefore, this paper designs and develops an automatic digital media image recognition system based on mean clustering algorithm. Firstly, this paper describes the concept and characteristics of digital media. Then, this paper also studies the application of mean clustering algorithm. Based on this, an automatic digital media image recognition system is designed, and the performance of the system is tested by simulation. Finally, the test results show that the algorithm can accurately identify media images. In general, the performance of the digital media image automatic recognition system based on mean clustering algorithm can meet the needs of target users.

Automatic Multiple Sensor Data Acquisition System in a Real-time Production Environment

One of the possible tasks for unmanned aerial vehicles (UAVs) is field capturing of object images. The field capturing of object images (scenes) is possible owing to the UAV equipped with photographic cameras, TV cameras, infrared camer-as or synthetic aperture radars (SAR). The result of the recognition is a metric mapping of space, i.e. 2D flat images. In order to increase the quality of image recognition, it is necessary to search for and develop stereoscopic visualization with the possibility of its mobile use. A pioneering approach presented in the research paper is using a UAV with an imagery intelligence system based on structured light technology for air reconnaissance of object over a selected area or in a given direction in the field. The outcome of imagery intelligence is a three-dimensional (3D imaging) information on the geometry of an observed scene. The visualization with a stereoscopic interface proposed in the work allows for a natural perception of the depth of the scene and mutual spatial relationships, as well as seeing which objects are closer and which are further. The essence of the article is to present the application of three-dimensional vision measurement technology on UAVs. The paper presents an analysis of the possibilities of using UAVs for image recognition and a method of image recognition based on the technology of structural lighting using the method of projection of Gray’a fringes and codes. The designed image recognition system based on the structural lighting technology is described. It also discusses task modules forming a measuring head, i.e., projection, detection and calculation modules, and the exchange of control or measurement data between imaging system components. It presents the results of tests on the possibility of rapidly acquiring images using a UAV. The test results and the analyses indicate that using a UAV with an imaging technology based on structural light can contribute to improving the abilities to detect, identify, locate and monitor objects at close range, within a selected direction outdoors or indoors.

The aim of this work was the implementation of an identification and evaluation methodology for external potato damage detection. A system for automatic image recognition was used and a methodology validation, by comparison with human visual selection, was performed. The potato surface image was acquired with a monochromatic video camera that operated in the visible spectrum and in the near infrared. This device was connected to a frame grabber card, interfaced to a PC, for image acquisition and elaboration. The software for the image elaboration has enabled the definition of algorithms for the automatic recognition and measurement of the damaged area. The obtained data were compared with the human visual evaluation demonstrating an adequate level of reliability of the applied methodology.

This paper presents an automatic fruit recognition system for classifying and identifying fruit types. The work exploits the fruit shape and color, to identify each image feature. The proposed system includes three phases namely: pre-processing, feature extraction, and classification phases. In the pre-processing phase, fruit images are resized to 90 x 90 pixels in order to reduce their color index. In feature extraction phase, the proposed system uses scale invariant feature transform (SIFT) and shape and color features to generate a feature vector for each image in the dataset. For classification phase, the proposed model applies K-Nearest Neighborhood (K-NN) algorithm classification, and support vector machine (SVM) algorithm of different kinds of fruits. A series of experiments were carried out using the proposed model on a dataset of 178 fruit images. The results of carrying out these experiments demonstrate that the proposed approach is capable of automatically recognize the fruit name with a high degree of accuracy.

Since health care on foods is drawing people's attention recently, a system that can record everyday meals easily is being awaited. In this paper, we propose an automatic food image recognition system for recording people's eating habits. In the proposed system, we use the Multiple Kernel Learning (MKL) method to integrate several kinds of image features such as color, texture and SIFT adaptively. MKL enables to estimate optimal weights to combine image features for each category. In addition, we implemented a prototype system to recognize food images taken by cellular-phone cameras. In the experiment, we have achieved the 61.34% classification rate for 50 kinds of foods. To the best of our knowledge, this is the first report of a food image classification system which can be applied for practical use.